How satish-shrestha-4u/restrodine-restaurant-intelligence works
RestroDine is a Streamlit restaurant-intelligence dashboard backed by synthetic restaurant data and precomputed analytical outputs. Managers explore financial performance, a weather-aware 14-day revenue forecast, workforce requirements and roster coverage, customer feedback and RFM segments, and menu profitability. The documented analytical workflow prepares data, produces forecasts and planning/management analyses, then presents saved outputs in the app; the forecast also feeds workforce planning. The source excerpts show forecast/weather and staffing logic, but not the notebook implementations or the app’s full data-loading code, so those links rely on README statements.
Main entry points: forecast_pipeline.py Revenue forecasting · outputs Analytical outputs · data_clean Clean datasets · 01a_data_cleaning.ipynb Data preparation
Components 16
Data preparation
- Synthetic source data
data - Data preparation
notebooks/01a_data_cleaning.ipynb - Clean datasets
data_clean
Business analytics
- Revenue analysis
notebooks/02_revenue_intelligence.ipynb
Forecast and workforce
- Revenue forecasting
forecast_pipeline.py - Weather service
- Workforce planning
forecast_pipeline.py - Workforce analysis
notebooks/03_workforce_intelligence.ipynb - Saved forecast model
models/restrodine_prophet_calendar_weather.json
Customer and menu
- Customer intelligence
notebooks/04_customer_intelligence.ipynb - Menu engineering
notebooks/05_menu_intelligence.ipynb
Dashboard and storage
- Analytical outputs
outputs - Streamlit dashboard
app.py - MySQL database
data/schema.sql - Database loader
load_database.py
Other components
- Restaurant manager
Connections 17
- Synthetic source data → Data preparation: prepares
README.md - Data preparation → Clean datasets: produces
README.md - Clean datasets → Revenue analysis: analyzes
README.md - Revenue analysis → Revenue forecasting: informs
README.md - Revenue forecasting → Weather service: requests weather
forecast_pipeline.py - Saved forecast model → Revenue forecasting: loads model
README.md - Revenue forecasting → Workforce planning: provides demand
README.md - Workforce planning → Workforce analysis: supports analysis
README.md - Clean datasets → Customer intelligence: analyzes
README.md - Clean datasets → Menu engineering: analyzes
README.md - Revenue forecasting → Analytical outputs: writes forecasts
README.md - Workforce planning → Analytical outputs: writes planning results
README.md - Customer intelligence → Analytical outputs: produces insights
README.md - Menu engineering → Analytical outputs: produces insights
README.md - Analytical outputs → Streamlit dashboard: reads results
README.md - Restaurant manager → Streamlit dashboard: explores insights
README.md - Database loader → MySQL database: loads tables
load_database.py